GLM 4.5 vs Kimi K2 Thinking
Kimi K2 Thinking leads GLM 4.5 on the Artificial Analysis Intelligence Index, 22.0 to 12.8, at about the same output price ($2.50 vs $2.20 per million). Updated October 22, 2026; 24 benchmarks have a result for both.
GLM 4.5 or Kimi K2 Thinking: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GLM 4.5 for output tokens 1.1x cheaper ($2.20 vs $2.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
- Shared results
- 24
- GLM 4.5 only
- 37
- Kimi K2 Thinking only
- 6
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Kimi K2 Thinking
Kimi K2 Thinking leads, 22.0 against 12.8.
Same board, both measured
Reasoning
GPQA Diamond
Kimi K2 Thinking
Kimi K2 Thinking leads, 78.5% against 72.2%.
Same board, both measured
Math
AIME
GLM 4.5
GLM 4.5 leads, 86.7% against 85.4%.
Same board, both measured
Knowledge
MMLU Pro
GLM 4.5
GLM 4.5 leads, 81.2% against 81.1%.
Same board, both measured
Web design
Design Arena: websites
GLM 4.5
GLM 4.5 leads, 1169 against 1113.
Same board, both measured
Long documents
Listed context window
Kimi K2 Thinking
Kimi K2 Thinking takes 262K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GLM 4.5
GLM 4.5 $0.0017, Kimi K2 Thinking $0.0019 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Kimi K2 Thinking has the number, $0.61.
Directional only
At a glance
- Coding index
- GLM 4.5 not benchmarked, Kimi K2 Thinking not benchmarked.
- Widest category
- Agentic work, 50.0 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GLM 4.5 43.0% against Kimi K2 Thinking 93.0%, 50.0 points apart on a 0 to 100 scale.
- Output price
- GLM 4.5 $2.20 against Kimi K2 Thinking $2.50 per million output tokens, 1.1x apart.
- Context window
- GLM 4.5 takes 131K tokens, Kimi K2 Thinking 262K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GLM 4.5 | Bars | Kimi K2 Thinking | Ties |
|---|---|---|---|---|
| Coding | 2 | 4 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 2 | 2 | ||
| Knowledge | 3 | 3 | ||
| Web design | 1 | 0 | ||
| General | 0 | 2 | ||
| All shared boards | 8 | 16 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index24
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| SWE-bench Verified | 64.2% | 63.4% | GLM 4.5 |
| LiveCodeBench (Vals AI) | 67.5% | 63.1% | GLM 4.5 |
| SWE-bench Verified (Vals AI) | Not measured | 60.2% | Only Kimi K2 Thinking measured |
| LiveCodeBench (Artificial Analysis run) | 73.8% | 85.3% | Kimi K2 Thinking |
| Terminal-Bench Hard (Artificial Analysis run) | 22.0% | 31.1% | Kimi K2 Thinking |
| Terminal-Bench | Not measured | 35.7% | Only Kimi K2 Thinking measured |
| WeirdML | 40.6% | 42.8% | Kimi K2 Thinking |
| ALE-Bench | 344.8 | 597.5 | Kimi K2 Thinking |
| LMArena Text: coding | 1434 | Not measured | Only GLM 4.5 measured |
| LMArena Text: software and IT | 1440 | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.8 | 22.0 | Kimi K2 Thinking |
| Epoch Capabilities Index | Not measured | 145.8 | Only Kimi K2 Thinking measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 43.0% | 93.0% | Kimi K2 Thinking |
| METR time horizons | Not measured | 59.2% | Only Kimi K2 Thinking measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| GPQA Diamond | 72.2% | 78.5% | Kimi K2 Thinking |
| GPQA Diamond (Artificial Analysis run) | 78.2% | 83.8% | Kimi K2 Thinking |
| Humanity's Last Exam (Artificial Analysis run) | 13.0% | 23.8% | Kimi K2 Thinking |
| LMArena Text: hard prompts | 1429 | Not measured | Only GLM 4.5 measured |
| LMArena Text: expert | 1433 | Not measured | Only GLM 4.5 measured |
| LMArena Text: hard prompts in English | 1429 | Not measured | Only GLM 4.5 measured |
| Kagi LLM Benchmark | 57.9% | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| AIME | 86.7% | 85.4% | GLM 4.5 |
| MATH 500 (Vals AI) | 94.0% | Not measured | Only GLM 4.5 measured |
| MGSM (Vals AI) | 90.8% | 90.2% | GLM 4.5 |
| AA Math Index | 73.7 | 94.7 | Kimi K2 Thinking |
| AIME 2025 (Artificial Analysis run) | 73.7% | 94.7% | Kimi K2 Thinking |
| LMArena Text: math | 1427 | Not measured | Only GLM 4.5 measured |
| LMArena Text: mathematical work | 1430 | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index33
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| MMLU Pro | 81.2% | 81.1% | GLM 4.5 |
| LegalBench (Vals AI) | 75.6% | 80.2% | Kimi K2 Thinking |
| CaseLaw (Vals AI) | Not measured | 65.7% | Only Kimi K2 Thinking measured |
| CorpFin (Vals AI) | 61.0% | 60.6% | GLM 4.5 |
| TaxEval (Vals AI) | 72.4% | 71.7% | GLM 4.5 |
| MedQA (Vals AI) | 90.0% | 92.6% | Kimi K2 Thinking |
| MMLU Pro (Artificial Analysis run) | 83.5% | 84.8% | Kimi K2 Thinking |
| LMArena Text: science | 1444 | Not measured | Only GLM 4.5 measured |
| LMArena Text: medicine and healthcare | 1455 | Not measured | Only GLM 4.5 measured |
| LMArena Text: legal and government | 1438 | Not measured | Only GLM 4.5 measured |
| LMArena Text: business and finance | 1420 | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 7 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Design Arena: websites | 1169 | 1113 | GLM 4.5 |
| Design Arena: UI components | 1141 | Not measured | Only GLM 4.5 measured |
| Design Arena: game dev | 1144 | Not measured | Only GLM 4.5 measured |
| Design Arena: data viz | 1159 | Not measured | Only GLM 4.5 measured |
| Design Arena: 3D | 1170 | Not measured | Only GLM 4.5 measured |
| Design Arena: all code categories | 1165 | Not measured | Only GLM 4.5 measured |
| Design Arena: SVG | 1096 | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| IFBench | 44.1% | 68.1% | Kimi K2 Thinking |
| Long context reasoning (AA-LCR) | 52.7% | 72.0% | Kimi K2 Thinking |
| Creative writing (Lech Mazur) | 73.4% | Not measured | Only GLM 4.5 measured |
| CL-bench | Not measured | 17.6% | Only Kimi K2 Thinking measured |
| LMArena Text | 1430 | Not measured | Only GLM 4.5 measured |
| LMArena Text: instruction following | 1404 | Not measured | Only GLM 4.5 measured |
| LMArena Text: creative writing | 1395 | Not measured | Only GLM 4.5 measured |
| LMArena Text: English | 1437 | Not measured | Only GLM 4.5 measured |
| LMArena Text: non-English | 1417 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Chinese | 1465 | Not measured | Only GLM 4.5 measured |
| LMArena Text: German | 1407 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Japanese | 1415 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Korean | 1380 | Not measured | Only GLM 4.5 measured |
| LMArena Text: French | 1418 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Spanish | 1454 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Russian | 1413 | Not measured | Only GLM 4.5 measured |
| LMArena Text: Polish | 1422 | Not measured | Only GLM 4.5 measured |
| LMArena Text: multi-turn | 1415 | Not measured | Only GLM 4.5 measured |
| LMArena Text: longer queries | 1412 | Not measured | Only GLM 4.5 measured |
| LMArena Text: writing and language | 1403 | Not measured | Only GLM 4.5 measured |
| LMArena Text: entertainment and media | 1404 | Not measured | Only GLM 4.5 measured |
| Neither model has a result on the other 25 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.5 | Kimi K2 Thinking | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GLM 4.5 costs less
Repository review
50K input + 3K output tokens
GLM 4.5 costs less
Agent loop
200K input + 10K output tokens
GLM 4.5 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Z.ai GLM 4.5 | MoonshotAI Kimi K2 Thinking |
|---|---|---|
| Maker | Z.ai | Moonshot AI |
| Weights | Open weights | Open weights |
| Released | July 25, 2025 | November 6, 2025 |
| Context window | 131K | 262K |
| Input $/Mtok | $0.60 | $0.60 |
| Output $/Mtok | $2.20 | $2.50 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 1 |
| Cost per solved task | Not computable | $0.61 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.5 better than Kimi K2 Thinking for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GLM 4.5 for output tokens 1.1x cheaper ($2.20 vs $2.50 per million) and work measured by LiveCodeBench (Artificial Analysis run) or Terminal-Bench Hard (Artificial Analysis run), where it leads.
Which is cheaper, GLM 4.5 or Kimi K2 Thinking?
GLM 4.5 costs $0.60 per million input tokens and $2.20 per million output tokens; Kimi K2 Thinking costs $0.60 and $2.50. Cost per solved task is known for Kimi K2 Thinking only.
Which has the bigger context window, GLM 4.5 or Kimi K2 Thinking?
Kimi K2 Thinking, with 262K tokens against 131K.
How many benchmarks is the GLM 4.5 vs Kimi K2 Thinking comparison based on?
24 benchmarks have a result for both models as of October 22, 2026. GLM 4.5's coding index rests on 0 independent benchmarks and Kimi K2 Thinking's on 1. Where only one model has a result, the page says so instead of naming a winner.